Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 76 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1062638 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2252. Min Act: -0.0001

Data Index: 771239 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1041450 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1985. Min Act: -0.0000

Data Index: 686838 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1033792 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1973. Min Act: 0.0000

Data Index: 1354724 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1153701 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1906. Min Act: -0.0000

Data Index: 654480 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1838. Min Act: -0.0001

Data Index: 201321 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1763. Min Act: -0.0000

Data Index: 94655 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1812. Min Act: -0.0000

Data Index: 248566 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1807. Min Act: -0.0000

Data Index: 4042 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1346130 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1720. Min Act: -0.0000

Data Index: 19293 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1718. Min Act: -0.0001

Data Index: 570916 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1706. Min Act: -0.0000

Data Index: 294579 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1693. Min Act: -0.0000

Data Index: 108798 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1694. Min Act: -0.0000

Data Index: 994170 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1675. Min Act: -0.0001

Data Index: 280739 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.2372. Min Range: -0.2372

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1031246 (C4 (Web Text))

Max Activating Token Index: 644